Retrieval pipelines, vector search, chunking and reranking: how models are grounded in a corpus instead of their weights.
arXiv:2610.27549v1 Announce Type: new Abstract: Task transition detection aims to identify when a person shifts from one task to another, providing a foundation for continuous health monitoring and t...
arXiv:2610.28555v1 Announce Type: cross Abstract: Statistical learning in high dimensions suffers from the curse of dimensionality. Fortunately, many functions of practical interest are compositional...
arXiv:2608.21755v2 Announce Type: replace Abstract: Long-horizon agents require more than retrieval over stored conversations: they must preserve source evidence, revise outdated knowledge, and disti...
FRAGMENT is a two‑stage generative framework that models documents as typed relational graphs, factorizing the joint distribution into structure and content components. The first stage, the Architect, uses a causally masked Transformer to autoregressively generate graph topology and spatial relations, while the second stage, the Builder, employs a GATv2-based graph attention network to add bounding boxes, text, and visual style attributes. The framework provides explicit likelihood models for anomaly scoring and supports prompt‑conditioned, entity‑aware editing via cross‑attention.
arXiv:2610.28010v1 Announce Type: new Abstract: The integration of Large Language Models and Reinforcement Learning offers a promising direction for complex sequential decision-making tasks, such as...
arXiv:2505.23442v2 Announce Type: replace Abstract: Knowledge graphs (KGs) provide structured representations of entities and relations, and underpin data management and Web applications such as sear...
arXiv:2605.12292v2 Announce Type: replace Abstract: Benchmarking tabular learning has revealed the benefit of dedicated architectures, pushing the state of the art. But real-world tables often contai...
arXiv:2610.26865v1 Announce Type: new Abstract: Retrieval-augmented speech translation improves rare terminology, but systems such as RASST still assume that users provide a glossary before each sess...
arXiv:2610.27109v1 Announce Type: cross Abstract: Spoken interaction is moving from alternating turns to full-duplex conversation, where an agent listens while speaking. Learning this coordination re...
arXiv:2610.27273v1 Announce Type: cross Abstract: Multi-vector retrieval models such as ColBERT often outperform single-vector models of comparable scale by matching queries and documents at the toke...
arXiv:2610.27678v1 Announce Type: cross Abstract: Electromyography (EMG) provides a non-invasive means of decoding silently articulated speech into text, but accurate decoding remains challenging due...
arXiv:2604.22555v3 Announce Type: replace Abstract: Estimating racial disparity requires individual-level race data, which are often unavailable due to the sensitivity of collecting such information....
arXiv:2410.21647v5 Announce Type: replace-cross Abstract: Recently, a number of repository-level code generation benchmarks-such as CoderEval, DevEval, RepoEval, RepoBench, and LongCodeArena-have eme...
arXiv:2610.27104v1 Announce Type: new Abstract: Reliable language-guided perception is essential for embodied agents, where questions about objects, events, and their locations must be answered from...
The paper introduces Pangaea-Latents, an extension of the Pangaea benchmark that provides frozen embeddings from five geospatial foundation models (GFMs) across eleven datasets, showing that these embeddings are neither redundant nor disjoint. It then proposes GeoMixture, a framework that aligns a Vision Transformer (ViT) to multiple GFMs per dataset using a multi-representation alignment (mREPA) objective, resulting in an encoder that achieves the best average rank across nine Pangaea datasets while maintaining cross-task consistency.
arXiv:2610.27829v1 Announce Type: new Abstract: Multimodal retrieval-augmented generation over visually rich documents requires evidence at a finer granularity than entire pages. Existing visual retr...
arXiv:2610.27890v1 Announce Type: new Abstract: Endoscopic video contains state transitions induced by camera displacement, deformable tissue, and instrument interaction, yet existing pre-training me...
arXiv:2610.28511v1 Announce Type: new Abstract: Tactile-visual-language models combine vision and touch through a shared language space to recognize objects and materials. In real-world deployment, c...
arXiv:2610.28524v1 Announce Type: new Abstract: Video generation models can create realistic-looking video footage from images and text prompts. Some of the recent advances have raised concerns about...
arXiv:2507.21917v2 Announce Type: replace Abstract: Analyzing digitized artworks requires both visual interpretation and deep artistic, contextual, and historical knowledge. We introduce ArtSeek, a m...